Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    tro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     killing
    -0.06
     Chern
    -0.06
    ��
    -0.06
     método
    -0.06
    显
    -0.06
     Без
    -0.06
     उच
    -0.06
    顯
    -0.06
     UNIQUE
    -0.06
    ίθ
    -0.06
    POSITIVE LOGITS
     rád
    0.07
     리그
    0.07
    ":"","
    0.06
    .subtitle
    0.06
    ?p
    0.06
    ธน
    0.06
    multi
    0.06
     yasak
    0.06
     hashmap
    0.06
    duration
    0.06
    Act Density 0.014%

    No Known Activations